Commit first working prototype

.bumpversion.cfg

@@ -0,0 +1,8 @@
+[bumpversion]
+current_version = 0.1.0
+commit = True
+tag = True
+
+[bumpversion:file:README.md]
+
+[bumpversion:file:dna_mutator/version.py]

.github/workflows/build.yml

@@ -0,0 +1,25 @@
+name: build
+
+on: [push, workflow_dispatch]
+
+jobs:
+  build:
+
+    runs-on: ubuntu-22.04
+
+    steps:
+      - uses: actions/checkout@v2
+      - name: Set up Python 3.9
+        uses: actions/setup-python@v2
+        with:
+          python-version: '3.9'
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install pytest pytest-cov
+      - name: Test pip installation
+        run: |
+          pip install -e .
+      - name: Test with pytest
+        run: |
+          python -m pytest --cov dna_mutator

.gitignore

@@ -20,6 +20,7 @@ parts/
 sdist/
 var/
 wheels/
+pip-wheel-metadata/
 share/python-wheels/
 *.egg-info/
 .installed.cfg
@@ -49,7 +50,6 @@ coverage.xml
 *.py,cover
 .hypothesis/
 .pytest_cache/
-cover/
 
 # Translations
 *.mo
@@ -72,7 +72,6 @@ instance/
 docs/_build/
 
 # PyBuilder
-.pybuilder/
 target/
 
 # Jupyter Notebook
@@ -83,9 +82,7 @@ profile_default/
 ipython_config.py
 
 # pyenv
-#   For a library or package, you might want to ignore these files since the code is
-#   intended to run in multiple environments; otherwise, check them in:
-# .python-version
+.python-version
 
 # pipenv
 #   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
@@ -94,24 +91,7 @@ ipython_config.py
 #   install all needed dependencies.
 #Pipfile.lock
 
-# poetry
-#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
-#   This is especially recommended for binary packages to ensure reproducibility, and is more
-#   commonly ignored for libraries.
-#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
-#poetry.lock
-
-# pdm
-#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
-#pdm.lock
-#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
-#   in version control.
-#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
-.pdm.toml
-.pdm-python
-.pdm-build/
-
-# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
 __pypackages__/
 
 # Celery stuff
@@ -147,16 +127,3 @@ dmypy.json
 
 # Pyre type checker
 .pyre/
-
-# pytype static type analyzer
-.pytype/
-
-# Cython debug symbols
-cython_debug/
-
-# PyCharm
-#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
-#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
-#  and can be added to the global gitignore or merged into this file.  For a more nuclear
-#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
-#.idea/

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 Edinburgh Genome Foundry
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -1 +1,41 @@
-# Mutator
+<p align="center">
+<img alt="EGF logo" title="EGF" src="images/egf.png" width="120">
+</p>
+
+# DNA Mutator
+
+![version](https://img.shields.io/badge/current_version-0.1.0-blue)
+[![build](https://github.com/Edinburgh-Genome-Foundry/dna_mutator/actions/workflows/build.yml/badge.svg)](https://github.com/Edinburgh-Genome-Foundry/dna_mutator/actions/workflows/build.yml)
+
+Create variants of DNA sequences.
+
+This repository is based on the software code of a dissertation project (B237870) for the MSc Bioinformatics program at the University of Edinburgh.
+
+## Install
+
+```bash
+pip install git+https://github.com/Edinburgh-Genome-Foundry/mutator.git
+```
+
+## Usage
+
+```python
+import dna_mutator as mutator
+record = mutator.Mutator.read_genbank("EGF.gb")
+mut = mutator.Mutator(record)
+mut.DelN()
+mut.write_all_records("variants")
+```
+
+## Versioning
+
+DNA Mutator uses the [semantic versioning](https://semver.org) scheme.
+
+## License = MIT
+
+DNA Mutator is free/libre and open-source software, which means the users have the freedom to run, study, change and distribute the software.
+
+DNA Mutator was written at the [Edinburgh Genome Foundry](https://edinburgh-genome-foundry.github.io/)
+by [B237870](https://github.com/B237870-2024) and [Peter Vegh](https://github.com/veghp).
+
+Copyright 2024 Edinburgh Genome Foundry, University of Edinburgh

dna_mutator/Mutator.py

@@ -0,0 +1,148 @@
+import os
+import random
+
+import pandas
+
+from Bio import SeqIO
+from Bio.Seq import Seq, MutableSeq
+from Bio.SeqRecord import SeqRecord
+from Bio.SeqFeature import SeqFeature, FeatureLocation
+
+
+class Mutator:
+    """Class to generate simulations of structural and single nucleotide variants.
+
+
+    **Parameters**
+
+    **reference**
+    > A `SeqRecord` instance.
+
+    **library_size**
+    > Library size (`int`).
+    """
+
+    def __init__(self, reference, library_size=10):
+        self.reference = reference
+        self.library_size = library_size
+        self.variant_records = []
+
+    def write_sample_sheet(self, csv_file):
+        """Create a sample sheet (for use with Sequeduct)"""
+        barcode_dir = [
+            "barcode" + ("{0:02d}".format(i + 1))
+            for i in range(len(self.variant_records))
+        ]
+
+        variants = [variant_record.id for variant_record in self.variant_records]
+        df_variants = pandas.DataFrame({"Sample": variants, "Barcode_dir": barcode_dir})
+        df_variants.to_csv(csv_file, index=False)
+
+    @staticmethod
+    def subtract_bases(seq, pos, n):
+        """Substract N bases from a sequence
+
+
+        **Parameters**
+
+        **seq**
+        > `Seq` instance.
+
+        **pos**
+        > Location of change (`int`).
+
+        **n**
+        > Number of bases to subtract (`int`).
+        """
+        modified_sequence = MutableSeq(seq)
+        deleted_sequence = modified_sequence[pos : pos + n]
+        del modified_sequence[pos : pos + n]
+
+        return (
+            modified_sequence,
+            pos,
+            deleted_sequence,
+        )
+
+    @staticmethod
+    def get_random_pos(record, n=1):
+        """Get n different random positions in a record"""
+        positions = random.sample(range(0, len(record)), n)
+
+        return positions
+
+    @staticmethod
+    def read_genbank(genbank, use_file_name_as_id=True):
+        """Get the reference sequence and features from input file
+
+        **Parameters**
+
+        **genbank**
+        > Path to Genbank file (`str`).
+
+        **use_file_name_as_id**
+        > Replace record id and name with the filename (`bool`).
+        """
+        record = SeqIO.read(genbank, "genbank")
+        if use_file_name_as_id:
+            record.name = os.path.splitext(os.path.basename(genbank))[0]
+            record.id = record.name
+
+        return record
+
+    @staticmethod
+    def write_genbank(record, file_name):
+        """Write SeqRecord to a Genbank file"""
+        SeqIO.write(record, file_name, "gb")
+
+    def write_all_records(self, dir_name):
+        """Write original record and all variants into a directory"""
+        extension = ".gb"  # standard file ext for GenBank files
+        os.mkdir(dir_name)
+        # ORIGINAL REFERENCE RECORD
+        ref_path = os.path.join(dir_name, self.reference.id + extension)
+        self.write_genbank(self.reference, ref_path)
+        # VARIANTS
+        for variant in self.variant_records:
+            variant_path = os.path.join(dir_name, variant.id)
+            self.write_genbank(variant, variant_path + extension)
+
+    def DelN(self, bases=1):
+        """Simulate N base deletion"""
+        positions = self.get_random_pos(self.reference, n=self.library_size)
+        for i in range(self.library_size):
+            position = positions[i]
+            modified_sequence, position, deleted_sequence = self.subtract_bases(
+                self.reference.seq, position, bases
+            )
+            if len(deleted_sequence) == 1:  # show the letter if there's only one
+                suffix = str(deleted_sequence)
+            else:
+                suffix = str(len(deleted_sequence))
+            # We append the original name according to nomenclature:
+            variant_name = self.reference.id + "_" + str(position) + "D" + suffix
+            variant_record = SeqRecord(
+                Seq(modified_sequence),
+                id=variant_name,
+                name=variant_name,
+                annotations={"molecule_type": "DNA", "topology": "circular"},
+            )
+            label = "@mutator(del)"
+            description = (
+                "Deletion in position "
+                + str(position)
+                + " of "
+                + str(bases)
+                + " bases ("
+                + str(deleted_sequence)
+                + ")"
+            )
+            feature = SeqFeature(
+                FeatureLocation(position, position),
+                type="misc_feature",
+                id="@mutator",
+                qualifiers={"label": label, "note": description},
+            )
+            variant_record.features.append(feature)
+
+            self.variant_records.append(variant_record)

dna_mutator/__init__.py

@@ -0,0 +1 @@
+from .Mutator import Mutator

dna_mutator/version.py

@@ -0,0 +1 @@
+__version__ = "0.1.0"

pypi-readme.rst

@@ -0,0 +1,33 @@
+DNA Mutator
+=============================
+
+Creating variants of DNA sequences
+
+
+**Install:**
+
+.. code:: bash
+
+    pip install dna_mutator
+
+
+**Web documentation:**
+
+`<https://edinburgh-genome-foundry.github.io/dna_mutator/>`_
+
+
+**Github page:**
+
+`<https://github.com/Edinburgh-Genome-Foundry/dna_mutator>`_
+
+
+**License:** MIT, Copyright 2024 Edinburgh Genome Foundry, University of Edinburgh
+
+
+More biology software
+---------------------
+
+.. image:: https://raw.githubusercontent.com/Edinburgh-Genome-Foundry/Edinburgh-Genome-Foundry.github.io/master/static/imgs/logos/egf-codon-horizontal.png
+  :target: https://edinburgh-genome-foundry.github.io/
+
+DNA Mutator is part of the `EGF Codons <https://edinburgh-genome-foundry.github.io/>`_ synthetic biology software suite for DNA design, manufacturing and validation.

setup.py

@@ -0,0 +1,20 @@
+from setuptools import setup, find_packages
+
+version = {}
+with open("dna_mutator/version.py") as fp:
+    exec(fp.read(), version)
+
+setup(
+    name="dna_mutator",
+    version=version["__version__"],
+    author="B237870",
+    author_email="egf-software@ed.ac.uk",
+    description="Create variants of DNA sequences",
+    long_description=open("pypi-readme.rst").read(),
+    long_description_content_type="text/x-rst",
+    license="MIT",
+    keywords="biology dna",
+    packages=find_packages(exclude="docs"),
+    include_package_data=True,
+    install_requires=["biopython"],
+)

tests/test_Mutator.py

@@ -0,0 +1,7 @@
+import pytest
+
+import dna_mutator
+
+
+def test_Mutator():
+    pass